Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

How to define a custom subagent in Codex

Alex Sidorenko

35,126 subscribers

34,795 views • 3 months ago •via X (Twitter)

Arts Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

How to use /goal in Codex to ship huge features

How to use /goal in Codex to ship huge features

Ryan Carson

24,086 views • 20 days ago

Introducing Guardrails 2.0 in ElevenAgents. Control how agents behave in production with a redesigned safety layer. You can define and enforce custom business policies. Or, toggle on pre-built protections to keep agents on-topic, on-brand, and resistant to manipulation.

ElevenLabs

50,145 views • 2 months ago

Codex has come a long way since April. Over the next two weeks, we’re releasing a series of videos to help you get better acquainted with Codex — starting with how to use the Codex CLI with GPT-5-Codex.

Codex has come a long way since April. Over the next two weeks, we’re releasing a series of videos to help you get better acquainted with Codex — starting with how to use the Codex CLI with GPT-5-Codex.

OpenAI Developers

190,153 views • 8 months ago

How to Implement a custom Accordion in react-native? using reanimated

How to Implement a custom Accordion in react-native? using reanimated

Ashu

31,861 views • 2 years ago

Quick demo of how I use Pi to offload tasks to Codex CLI with the pi-interactive-shell extension. Codex is notoriously tricky to prompt well so Pi reads the Codex prompting guide to generate a tailored meta-prompt, then launches Codex CLI in an overlay. pi install npm:pi-interactive-shell

Quick demo of how I use Pi to offload tasks to Codex CLI with the pi-interactive-shell extension. Codex is notoriously tricky to prompt well so Pi reads the Codex prompting guide to generate a tailored meta-prompt, then launches Codex CLI in an overlay. pi install npm:pi-interactive-shell

nicopreme

20,441 views • 4 months ago

How to make a custom grid floor to use in your animations in one minute!

How to make a custom grid floor to use in your animations in one minute!

Nikos

35,020 views • 1 year ago

Codex team is back in the kitchen with a really nice quality of life upgrade for subagents. With the advent of custom roles, they have also upgraded the TUI experience in two really meaningful ways. > All agents now get a name for better readability > Additionally, the agent role is declared. > Subagent name, role, and status are now color coded. > Subagent rendering was also optimized for readability > /agents slash command shows all agents, even 2+ layers deep. And here's the biggest and most important change. Subagent injection. Before, sometimes the orchestration agent would continue work and lose track of the work of a subagent. Now, when a subagent is blocked or completed, it injects a message back up the chain to ensure that the parent sees the message. This is a really big improvement overall, and leads to much more reliable inter-agent communication, reliability, and DX. In this example, I used the parent agent to spin up a worker agent, which then spawned two more "Spark" agents a second layer deep. I was able to easily tell them apart, switch between the threads, and see exactly what they were prompted. All of this will be available in update 0.105.0 I don't know who JIF is at OpenAI, but they are truly a legend.

Codex team is back in the kitchen with a really nice quality of life upgrade for subagents. With the advent of custom roles, they have also upgraded the TUI experience in two really meaningful ways. > All agents now get a name for better readability > Additionally, the agent role is declared. > Subagent name, role, and status are now color coded. > Subagent rendering was also optimized for readability > /agents slash command shows all agents, even 2+ layers deep. And here's the biggest and most important change. Subagent injection. Before, sometimes the orchestration agent would continue work and lose track of the work of a subagent. Now, when a subagent is blocked or completed, it injects a message back up the chain to ensure that the parent sees the message. This is a really big improvement overall, and leads to much more reliable inter-agent communication, reliability, and DX. In this example, I used the parent agent to spin up a worker agent, which then spawned two more "Spark" agents a second layer deep. I was able to easily tell them apart, switch between the threads, and see exactly what they were prompted. All of this will be available in update 0.105.0 I don't know who JIF is at OpenAI, but they are truly a legend.

am.will

78,267 views • 3 months ago

GPT 5.4 has been released... + 1M context window! Here's how to enable in Codex: → 1. ~/.codex/config.toml → 2. model = "gpt-5.4" → 3. model_context_window=1000000 → 4. model_auto_compact_token_limit=9000000 Run codex → 5. /statusline → 6. toggle context-window-size I didn't even realise Codex had a statusline tool!

GPT 5.4 has been released... + 1M context window! Here's how to enable in Codex: → 1. ~/.codex/config.toml → 2. model = "gpt-5.4" → 3. model_context_window=1000000 → 4. model_auto_compact_token_limit=9000000 Run codex → 5. /statusline → 6. toggle context-window-size I didn't even realise Codex had a statusline tool!

Chong-U

76,354 views • 3 months ago

Codex built me a full Memory Manager overnight using my new "Teams" strategy. Flawless first test. One prompt spun up 70 domain-expert subagents, organized into specialized teams, all working in parallel to one-shot the entire app while I slept. I've built over 200 custom subagent roles for this. Playbook dropping soon. This is a massive unlock for parallelization. I'll be improving this and testing it on much larger projects.

Codex built me a full Memory Manager overnight using my new "Teams" strategy. Flawless first test. One prompt spun up 70 domain-expert subagents, organized into specialized teams, all working in parallel to one-shot the entire app while I slept. I've built over 200 custom subagent roles for this. Playbook dropping soon. This is a massive unlock for parallelization. I'll be improving this and testing it on much larger projects.

am.will

31,458 views • 3 months ago

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.

Peter Gostev

66,675 views • 1 month ago

Here’s how to get started with Codex:

Here’s how to get started with Codex:

OpenAI Developers

426,350 views • 1 year ago

how to use custom format form in excel

how to use custom format form in excel

Tips Excel

40,857 views • 1 year ago

you can navigate to subagent sessions now for better visibility in opencode v0.5.2

you can navigate to subagent sessions now for better visibility in opencode v0.5.2

Adam

30,438 views • 10 months ago

How to get a Custom Wallpaper #VALORANT

How to get a Custom Wallpaper #VALORANT

Rem

516,341 views • 3 years ago

How to build a custom range hood

How to build a custom range hood

Christy

65,549 views • 1 month ago

Trying to explain to my normie friends how Codex works

Trying to explain to my normie friends how Codex works

am.will

16,882 views • 4 months ago

🚀 Notion → Replit, now automated with Custom MCPs Checkout the demo below on how to: ✅ Use Notion AI to generate a PRD for an app ✅ Use Replit Agent to build the app and integrate it with Notion database 🚀 ✅ Define in Notion. Build in Replit. From strategy to software in minutes. ✨

🚀 Notion → Replit, now automated with Custom MCPs Checkout the demo below on how to: ✅ Use Notion AI to generate a PRD for an app ✅ Use Replit Agent to build the app and integrate it with Notion database 🚀 ✅ Define in Notion. Build in Replit. From strategy to software in minutes. ✨

Replit ⠕

43,948 views • 6 months ago

Units are universally agentic. Your Unit can now be integrated with most tools that support custom model providers, including Cursor, Codex CLI, VS Code, and more. Here's Codex CLI setup in 30 seconds

Units are universally agentic. Your Unit can now be integrated with most tools that support custom model providers, including Cursor, Codex CLI, VS Code, and more. Here's Codex CLI setup in 30 seconds

Rei

14,983 views • 4 months ago

Here’s how I use Agentation + queuing messages in Codex to crank through frontend work much faster

Here’s how I use Agentation + queuing messages in Codex to crank through frontend work much faster

Ryan Carson

31,776 views • 3 months ago

How Does Quran Define a Kaafir?

How Does Quran Define a Kaafir?

Prachyam

28,504 views • 9 months ago